GNU bug report logs - #51787
GC takes more than 9 hours on berlin

Previous Next

Full log

Message #76 received at 51787 <at> debbugs.gnu.org (full text, mbox):

From: Bengt Richter <bokr <at> bokr.com>
To: Mathieu Othacehe <othacehe <at> gnu.org>
Cc: Ricardo Wurmus <rekado <at> elephly.net>, 51787 <at> debbugs.gnu.org
Subject: Re: bug#51787: Disk performance on ci.guix.gnu.org
Date: Mon, 20 Dec 2021 19:36:51 +0100

On +2021-12-20 17:59:33 +0100, Mathieu Othacehe wrote:
> 
> Hey,
> 
> > This is still pretty bad, but better than the <1M performance suggested
> > by previous runs.
> 
> Mmh interesting, I also have a x10 speed up on sdb by increasing the
> block size from 4k to 512k. I'm not sure what conclusion should we draw
> from this observation.
> 
> In particular for our most urging matter, /gnu/store/trash
> removal. Moving to a faster hard drive would definitely help here, but I
> still don't understand if that disk performance regression comes from
> Linux, the file-system fragmentation, or the disk itself.
> 
> >    READ: bw=1547MiB/s (1622MB/s), 1547MiB/s-1547MiB/s (1622MB/s-1622MB/s), io=3055MiB (3203MB), run=1975-1975msec
> >   WRITE: bw=527MiB/s (553MB/s), 527MiB/s-527MiB/s (553MB/s-553MB/s), io=1042MiB (1092MB), run=1975-1975msec
> 
> Wooh that's fast! On test could be to copy the /gnu/store/trash content
> to the SAN an observe how long that it takes for this operating to
> complete.

also might be interesting to copy to /dev/null
to see read rate alone on /gnu/store?

> 
> Thanks for your support on that complex topic :)
> 
> Mathieu
> 
> 
> 

-- 
Regards,
Bengt Richter

Previous Next

GNU bug tracking system
Copyright (C) 1999 Darren O. Benham, 1997,2003 nCipher Corporation Ltd, 1994-97 Ian Jackson.